EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Optimization of Multi-Task Efficient Offloading Strategy for Heterogeneous Edge Computing Based on Deep Reinforcement Learning

Sen Zhu

Journal of Computer Science and Artificial Intelligence · 11.02.2025 · 2 (1) · 22-28

DOI: 10.54097/cpmvcr09 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computer Science and Artificial Intelligence, online erschienen am 11.02.2025. Verfasst von Sen Zhu. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Edge computing is a computing paradigm that provides fast and efficient computing services to mobile devices by bringing resources closer to the edge of the network. However, current edge servers lack the computational power to handle the large volume of tasks generated by connected devices. Moreover, some mobile devices may not fully utilize their computational resources. In order to maximize the use of resources, a more sustainable and energy efficient computing paradigm was developed. Minimize the use of Mobile Edge Computing (MEC) servers for applications that run in random environments with unpredictable workloads. And utilizing available resource-constrained edge devices to keep resource-rich servers idle to handle any unpredictable larger workloads. Our focus is on optimizing device computation offloading to minimize the maximum task processing delay in the system. This problem has been proven to be NP-hard. To address this problem, we propose an efficient offloading algorithm based on deep Q-network (DQNEO). The algorithm effectively utilizes computational resources in the system and makes intelligent scheduling decisions based on system state information using deep reinforcement learning. Experimental results show that the DQNEO algorithm can reduce the system processing delay by converging to the optimal solution.

Zitieren

APA

Zhu, S. (2025). Optimization of Multi-Task Efficient Offloading Strategy for Heterogeneous Edge Computing Based on Deep Reinforcement Learning. Journal of Computer Science and Artificial Intelligence, 2(1), 22-28. https://doi.org/10.54097/cpmvcr09

Vancouver

Zhu S. Optimization of Multi-Task Efficient Offloading Strategy for Heterogeneous Edge Computing Based on Deep Reinforcement Learning. Journal of Computer Science and Artificial Intelligence. 2025;2(1):22-28. doi:10.54097/cpmvcr09

BibTeX
@article{Zhu2025,
  author = {Zhu, Sen},
  title = {Optimization of Multi-Task Efficient Offloading Strategy for Heterogeneous Edge Computing Based on Deep Reinforcement Learning},
  journal = {Journal of Computer Science and Artificial Intelligence},
  year = {2025},
  volume = {2},
  number = {1},
  pages = {22--28},
  doi = {10.54097/cpmvcr09}
}
Kostenlos starten →